configuring-auto-scaling-policies

Warn

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The generate_script function in scripts/generate_config.py uses chmod(0o755) to set the execution bit on generated shell scripts, allowing them to be run by the system.
  • [COMMAND_EXECUTION]: The scripts/generate_config.py script performs dynamic code generation by interpolating the content argument directly into a shell script template without validation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external workload metrics and user-supplied scaling requirements to generate executable logic.
  • Ingestion points: User-provided configuration details and external metric data processed via the generate_config.py script.
  • Boundary markers: Absent; there are no delimiters or instructions provided to the agent to distinguish between legitimate configuration data and potentially malicious instructions.
  • Capability inventory: The skill is granted broad shell access via the Bash(cmd:*) tool defined in SKILL.md.
  • Sanitization: Absent; the implementation lacks validation or escaping of the input content before it is embedded into generated shell scripts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 19, 2026, 10:09 PM
Security Audit — agent-trust-hub — configuring-auto-scaling-policies